© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2566
    Prev
    Next
    INDEX
    Explanations

    affirmative and negative statements in discussions or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to questions and affirmative answers (like "yes", "the answer is", "of course").

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.83
    featureID
    -0.75
    afficheront
    -0.71
     <=",
    -0.70
    <pad>
    -0.69
    <unused43>
    -0.69
     zwiſchen
    -0.69
    <unused41>
    -0.68
    <unused17>
    -0.68
    <unused42>
    -0.68
    POSITIVE LOGITS
     answer
    0.52
    答案
    0.37
    answer
    0.36
     yes
    0.36
     Yes
    0.36
     clue
    0.35
     answers
    0.34
    Answer
    0.33
     Answer
    0.33
     Pues
    0.33
    Activations Density 0.254%

    No Known Activations